Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Self-Evaluation Maintenance Model01:29

Self-Evaluation Maintenance Model

The Self-Evaluation Maintenance (SEM) model offers a psychological framework to understand how individuals’ self-esteem is influenced by the achievements of others, particularly those with whom they share close personal bonds. The SEM model operates when personal rather than social identity guides individuals. Central to this model is the notion that individuals have an inherent desire to preserve a favorable self-image, which is continuously shaped by interpersonal comparisons and...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Flow diversion in proximal superior cerebellar artery aneurysms: Systematic review of clinical outcomes and exploratory hemodynamic analysis.

Neurosurgical review·2026
Same author

GeNED.ar cohort: Neuroimaging Resource for Aging Studies in an Admixed Population from Argentina.

NeuroImage·2026
Same author

Problematic Alcohol Use and Decision-Making in High-Functioning Young Adults: roles of Fluid Intelligence, Risk Perception and Sex.

Substance use & misuse·2026
Same author

Motor Nerve Conduction of the Hypoglossal Nerve With F-Waves in Healthy Adults.

Muscle & nerve·2026
Same author

Recognition memory in individuals with mild cognitive impairment and Alzheimer's dementia: a systematic review.

Applied neuropsychology. Adult·2026
Same author

Program of Genomic Reference and Biobank of the Argentinian Population: A National Initiative for Genomic Equity and Population-Based Research in Argentina.

Biopreservation and biobanking·2025

相关实验视频

Updated: May 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

一个自我监督的深度学习模型,用于用有限的标记数据检测诊断性硫.

Delfina Braggio1,2, Hernán C Külsgaard3,4, Mariana Vallejo-Azar3,5

  • 1Consejo Nacional de Investigaciones Científicas y Técnicas, CONICET, Buenos Aires, Argentina. delfinabraggio@pladema.exa.unicen.edu.ar.

Neuroinformatics
|January 8, 2025
PubMed
概括

这项研究引入了一种深度学习模型,用于自动检测对角突 (ds),这是一个小但重要的大脑特征. 该模型实现了高精度,性能优于现有方法,并有助于人口层面分析.

关键词:
自动分类的自动分类.诊断上的硫.精细调整 微调 精细调整机器学习 机器学习三级硫三级硫是什么

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

710

相关实验视频

Last Updated: May 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

463
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

710

科学领域:

  • 神经科学是一个神经科学.
  • 医疗成像医学成像
  • 人工智能的人工智能

背景情况:

  • 硫是影响认知和行为的关键大脑结构.
  • 三级,像对角 (ds),很难自动检测.
  • ds对于语言处理至关重要,其流行率为50-60%.

研究的目的:

  • 开发和验证一个深度学习模型,用于准确地自动检测对角突 (ds).
  • 为了解决DS识别中现有的硫化物细分工具的局限性.
  • 探索自我监督和微调学习的应用,以有限的标记数据来完成这个任务.

主要方法:

  • 使用卷积式自编码器对未标记的大脑数据进行自我监督的学习.
  • 在有限的标记数据集上对预训练模型进行了微调,以用于DS检测.
  • 在手动标签中使用了封闭图来解释模型的可解释性,并分析了评分器间的可靠性.

主要成果:

  • 在测试组中获得了0.7176 (SD=0.0736) 的平均F1得分,在持有组中达到0.72.
  • 该模型的性能超过了标准软件和替代深度学习方法.
  • 解释性分析显示,该模型侧重于相邻的硫酸盐,类似于专家注释.

结论:

  • 拟议的深度学习模型提供了一种强大而准确的方法,用于自动检测对角突.
  • 微调方法有效地利用有限的标记数据用于专门的脑结构识别.
  • 该方法对调查DS流行率及其临床意义的人口水平研究具有前景.